Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Pandit, Parthe"'
Recent advances in machine learning have led to increased interest in reproducing kernel Banach spaces (RKBS) as a more general framework that extends beyond reproducing kernel Hilbert spaces (RKHS). These works have resulted in the formulation of re
Externí odkaz:
http://arxiv.org/abs/2411.11242
We study the Laplacian of the undirected De Bruijn graph over an alphabet $A$ of order $k$. While the eigenvalues of this Laplacian were found in 1998 by Delorme and Tillich [1], an explicit description of its eigenvectors has remained elusive. In th
Externí odkaz:
http://arxiv.org/abs/2410.07622
Kernel ridge regression (KRR) is a popular class of machine learning models that has become an important tool for understanding deep learning. Much of the focus has been on studying the proportional asymptotic regime, $n \asymp d$, where $n$ is the n
Externí odkaz:
http://arxiv.org/abs/2408.01062
Autor:
Mallinar, Neil, Beaglehole, Daniel, Zhu, Libin, Radhakrishnan, Adityanarayanan, Pandit, Parthe, Belkin, Mikhail
Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon where the test accuracy starts improving long after the model achieves 100% training accuracy in the training process. It is often taken as an example of "emerge
Externí odkaz:
http://arxiv.org/abs/2407.20199
Kernel methods are a popular class of nonlinear predictive models in machine learning. Scalable algorithms for learning kernel models need to be iterative in nature, but convergence can be slow due to poor conditioning. Spectral preconditioning is an
Externí odkaz:
http://arxiv.org/abs/2312.03311
Understanding the mechanism of how convolutional neural networks learn features from image data is a fundamental problem in machine learning and computer vision. In this work, we identify such a mechanism. We posit the Convolutional Neural Feature An
Externí odkaz:
http://arxiv.org/abs/2309.00570
Generative Adversarial Networks (GANs) are a popular formulation to train generative models for complex high dimensional data. The standard method for training GANs involves a gradient descent-ascent (GDA) procedure on a minimax optimization problem.
Externí odkaz:
http://arxiv.org/abs/2305.08277
Recent studies indicate that kernel machines can often perform similarly or better than deep neural networks (DNNs) on small datasets. The interest in kernel machines has been additionally bolstered by the discovery of their equivalence to wide neura
Externí odkaz:
http://arxiv.org/abs/2302.02605
In recent years neural networks have achieved impressive results on many technological and scientific tasks. Yet, the mechanism through which these models automatically select features, or patterns in data, for prediction remains unclear. Identifying
Externí odkaz:
http://arxiv.org/abs/2212.13881
Generative Adversarial Networks (GANs) are a widely-used tool for generative modeling of complex data. Despite their empirical success, the training of GANs is not fully understood due to the min-max optimization of the generator and discriminator. T
Externí odkaz:
http://arxiv.org/abs/2208.09938